Planning-aligned Token Compression for Long-Context Autonomous Driving 事件

Planning-aligned Token Compression for Long-Context Autonomous Driving arXiv:2606.07464v1 Announce Type: cross Abstract: Monolithic vision-action models represent an emerging paradigm in autonomous driving. However, this architecture produces token sequences that quickly exceed real-time computational budgets when encoding extended temporal context for complex interactions. While approaches like linear transformers and external memory try to make the context lightweight, token compression is mo